Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67608
    Prev
    Next
    INDEX
    Explanations

    occurrences of object-oriented programming syntax, particularly related to member accesses in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imp
    -0.50
     exp
    -0.49
     to
    -0.48
    点を
    -0.47
     tried
    -0.45
     ev
    -0.45
    者を
    -0.45
     consider
    -0.45
     inex
    -0.45
     braw
    -0.45
    POSITIVE LOGITS
     &___
    0.66
    setVerticalGroup
    0.58
    الدراسه
    0.57
     "..\..\..\
    0.57
     Infórmanos
    0.54
    webElementXpaths
    0.54
    Personendaten
    0.51
     ModelExpression
    0.50
     GenerationType
    0.50
     protoimpl
    0.50
    Activations Density 0.018%

    No Known Activations